NEW Midjourney UPDATE is a lot of FUN

Future Tech Pilot
23 Apr 202408:52

TLDRMidjourney 刚刚发布了一个新特性，即随机风格生成器，为创作带来乐趣。用户可以通过在提示中加入 'D-sref style reference' 和 'random' 来生成完全出乎意料的图像。例如，输入 'Batman srf random' 将产生一个未知风格的蝙蝠侠图像。该功能的核心在于发现并应用你喜欢的风格，比如将一个蝙蝠侠图片作为风格参考，用于生成新的图像。此外，用户还可以在 Midjourney 网站上使用该特性，通过调整参数如风格权重、角色权重、混沌值等来进一步定制生成的图像。视频还展示了如何利用 'CF character reference' 结合随机风格生成器来创建具有特定角色特征的图像。这个新特性不仅提供了一种新的方式来探索艺术风格，也使得创作过程更加灵活和有趣。

Takeaways

  • 🎉 Midjourney has released a new feature: a random style generator that creates unexpected image styles.
  • 📝 To use the feature, append 'D-sref style reference random' to your prompt to generate a random style.
  • 🌟 The purpose of the feature is to discover a style you like and then use it for future image generations.
  • 🔍 You can upscale a preferred image and use it as a style reference for new prompts, combining it with other elements like Wonder Woman and love stories.
  • 🌈 The new style can be transferred to new generations, resulting in a diverse range of artistic outcomes.
  • 📷 On the Midjourney website, you can input a prompt and use the 'random' option for style reference after setting your preferences.
  • 🖌️ The 'describe' feature helps you understand the style of an image by providing descriptive words and artist references.
  • 🔗 You can use an image link as a style reference in your prompt to influence the style of the generated images.
  • 📚 The 'Midjourney beginner course' mentioned offers a more structured approach to using AI, which can be found in the description below the video.
  • 🤖 Parameters such as style weight, character weight, chaos, and styze can be adjusted for more control over the generated image's style.
  • 🛠️ Character reference combined with style reference random allows for a unique blend of character and art style.
  • 🎲 Using the 'repeat' parameter lets you run the same prompt multiple times to see different random styles applied to your character.

Q & A

  • What is the new feature released by Midjourney that the speaker discusses?

    -The new feature released by Midjourney is a random style generator that allows users to create images with unexpected styles.

  • How does the random style generator work?

    -The random style generator works by using a style reference feature. Users write a prompt, add 'srf' (style reference), a space, and then the word 'random' at the end of the prompt.

  • What is the purpose of using the 'srf random' command in the prompt?

    -The 'srf random' command in the prompt is used to generate images in a completely unexpected style, providing a unique and fun experience for the user.

  • How can users find a style they like and use it in future generations?

    -Users can upscale an image they like, then use that image as a style reference in a new prompt by clicking and dragging the image into the prompt box after the 'srf' command.

  • What are the steps to use the random style generator on the Midjourney website?

    -On the Midjourney website, users can type their prompt, add 'srf' followed by a space and the word 'random', adjust settings like aspect ratio if needed, and then hit enter to generate the image.

  • How does the 'describe' feature help users understand the style of an image?

    -The 'describe' feature provides users with descriptive words or prompts that attempt to describe the style of an image. This can help users learn more about the style and how to replicate it in future generations.

  • What is the character reference feature and how does it work?

    -The character reference feature allows users to input an image of a character and use it as a reference for the style and appearance of characters in the generated images. It can be combined with the 'srf random' command for unique character styles.

  • How can users adjust the influence of the new style on the generated image?

    -Users can adjust the influence of the new style using the 'style weight' parameter, which has a value range between 0 and 1000. A higher value increases the impact of the new style on the image.

  • What is the 'chaos' parameter and how does it affect the generated image?

    -The 'chaos' parameter, with a value range between 0 and 100, controls the level of randomness or unpredictability in the generated image. Higher values result in more varied and chaotic styles.

  • How can users repeat the same prompt multiple times to see different outcomes?

    -Users can use the 'repeat' parameter followed by the number of times they want the prompt to run. This will generate multiple images with different random styles based on the same prompt.

  • What additional parameters can users include with 'srf random' for more control over the generated image?

    -Users can include parameters such as 'style weight', 'character weight', 'chaos', and 'styze' to fine-tune the influence of the style and character references on the generated image.

  • Where can users find more information about using these features in Midjourney?

    -Users can find more information and a structured look at these features in the Midjourney beginner course, which is mentioned in the description of the video.

Outlines

00:00

🎨 Exploring the Random Style Generator Feature

The video introduces a new feature from Wake Up Mid Journey called the random style generator. This feature creates unpredictable and fun styles for images based on a style reference prompt. The host demonstrates how to use the feature by inputting a prompt with 'D- sref style reference random' to generate a random style for Batman. The viewer is shown how to upscale a preferred style and apply it to future generations with a new prompt, like a love story involving Wonder Woman. The host also explains how to use the feature on the Mid Journey website, including adjusting settings like aspect ratio and using the 'describe' function to learn more about the style referenced.

05:00

📸 Applying Style References and Parameters for Enhanced Image Generation

The host continues to explore the random style generator by combining it with parameters and character references for more control over the image generation process. The video shows how to use a random style from a previous generation as a style reference for a new prompt, such as the Toronto skyline. The host also discusses the use of parameters like style weight (SW), character weight (CW), style (STYZE), and chaos (CHAOS) to fine-tune the influence of the style and character on the final image. The video concludes with a demonstration of how to use the repeat parameter to generate multiple variations of an image with a single prompt.

Mindmap

Keywords

💡Midjourney

Midjourney refers to a software or tool that is being discussed in the video. It is the platform where the new feature of a random style generator is introduced. The term is central to the video's theme as it is the subject of the tutorial and demonstration.

💡Random Style Generator

A feature within the Midjourney tool that generates random styles for images based on a given prompt. It is a key concept in the video as it is the main focus of the demonstration, showing how it can produce unexpected and creative visual results.

💡Style Reference

A command used within the Midjourney tool that allows users to specify a particular style for image generation. It is integral to the video's narrative as it is used to guide the viewer on how to apply a preferred style to future image generations.

💡Upscale

In the context of the video, 'upscale' refers to the process of selecting a generated image and using it as a reference for a new style. It is a technique demonstrated in the video to show how a chosen style can be applied to different subjects or prompts.

💡Prompt

A prompt in the context of Midjourney is a text input that guides the image generation process. It is a fundamental part of using the tool as it dictates the theme or subject of the generated images, as demonstrated in the video with examples like 'Batman' and 'Penguin dressed like a gentleman'.

💡Discord

Discord is mentioned as a platform where the Midjourney tool can be used, suggesting it is an interface for interacting with the tool. It is part of the video's content as the speaker guides viewers on how to use the tool within Discord.

💡Aspect Ratio

The aspect ratio is a parameter that can be adjusted in Midjourney to affect the shape of the generated images. It is mentioned in the video as one of the settings that users can modify to suit their preferences for image composition.

💡Character Reference

A parameter within Midjourney that allows users to input a specific character or subject into the image generation process. It is showcased in the video as a way to combine with the random style generator to create unique character representations.

💡Parameters

Parameters in the context of the video are settings or variables that can be adjusted within the Midjourney tool to control the style and appearance of the generated images. They are essential for customizing the image generation process, as shown with 'style weight', 'character weight', 'chaos', and 'repeat'.

💡Describe Feature

The 'describe' feature in Midjourney is used to analyze and provide descriptive words or styles based on an input image. It is highlighted in the video as a way for users to understand and articulate the style of an image for future use in image generation.

💡Style Weight

Style weight is a parameter in Midjourney that determines the influence of a chosen style on the generated image. It is demonstrated in the video as a way to balance the original character's features with the new style to achieve a desired artistic effect.

Highlights

Midjourney has released a new feature: a random style generator.

The random style generator creates unexpected image styles based on style references.

To use the feature, append 'srf random' to your prompt.

The resulting images from 'srf random' are completely unpredictable.

You can upscale a preferred style for future generations.

The feature allows transferring a liked style onto new generations.

An example prompt combines Wonder Woman with a love story in a specific style.

The 'describe' feature helps understand the style of an image with descriptive words.

On the Midjourney website, you can filter settings like aspect ratio for style generation.

The 'describe' feature on the website provides a list of descriptive words for a style.

You can use a random style on future prompts by dragging an image into the prompt box.

Parameters like style weight, character weight, chaos, and styze can be adjusted for unique results.

Style weight determines the influence of the new style on the generation.

Character weight allows the character to blend into the new art style.

The styze parameter enhances the beauty of the generation.

The chaos parameter can create more diversity in the generated styles.

The repeat parameter allows running the prompt multiple times for various outcomes.

Combining character reference with style reference random can produce unique and fun results.

The new feature is a lot of fun and offers a lot of creative possibilities.